13 papers in the archive · tier-1 watchlist.
AI-Var trains a neural network to minimise the variational DA cost function directly, producing accurate initial conditions without pre-existing analysis datasets in proof-of-concept tests.
Releases EUPPBench, a time-aligned forecast-observation dataset with evaluation methods and a first benchmark of 2 m temperature postprocessing.
Benchmarks, datasets & evaluationDeutscher Wetterdienst (DWD)ECMWFKarlsruhe Institute of Technology (KIT)Met OfficeMétéo-France (incl. CNRM)MeteoSwisscode
A neural network with Shapley values on ERA5 predictors explains 70% of European heatwave variability, with upper-level geopotential the largest contributor at 27%.
Reviews and analyses inductive biases (data, objectives, losses, architectures, optimisation) of deep-learning weather prediction models to guide more efficient, probabilistic designs.
Conditional GAN and U-Net generate high-resolution short-range precipitation maps from full NWP variables, reducing over-forecast bias; CGAN gives the most realistic output.
Downscaling & super-resolutionDeutscher Wetterdienst (DWD)Forschungszentrum Jülich / Jülich Supercomputing Centre
Probabilistic neural networks post-process ensemble precipitation at four stations, outperforming logistic regression and GLM for hourly precipitation and rain probability.
A CNN detects clouds in camera photos to build a forward operator, enabling convective-scale assimilation of cloud cover into the ICON-D2 model; proof of concept over 6 days.
Neural network and GLM correct COSMO-REA6 reanalysis wind speeds at 100 m after diagnostic wind-model downscaling, reducing RMSE by almost 30% in Central Europe.
Neural network blends two precipitation ensembles into calibrated hourly exceedance probabilities for +1 to +6 h, outperforming both inputs at all lead times.
Conceptual proposal for FAIR, reproducible HPC-based workflows for ML weather and precipitation forecasting, using the DeepRain project as a case.
Software, scaling & compressionDeutscher Wetterdienst (DWD)Forschungszentrum Jülich / Jülich Supercomputing Centre
Neural network combines RadVOR radar nowcasts with postprocessed COSMO-DE-EPS ensembles, giving calibrated precipitation threshold probabilities that beat both inputs for 1 to 6 h.
Review of statistical postprocessing methods for NWP forecasts and their challenges in big-data settings, with little explicit machine learning focus.
Post-processing & calibrationDeutscher Wetterdienst (DWD)ECMWFKarlsruhe Institute of Technology (KIT)KNMI (Royal Netherlands Meteorological Institute)MET Norway (Norwegian Meteorological Institute)Met OfficeMétéo-France (incl. CNRM)MeteoSwiss
Uses optical-flow error from satellite imagery as features for tree and neural classifiers to predict lightning up to five hours ahead, with 96% accuracy at 15 minutes.
